発音時刻の直交性を考慮したNMFによるエレキベースの音高・発音時刻推定

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2016/12/01

タイトル(英語): Pitch and Onset Time Estimation of Electric Bass by Non-negative Matrix Factorization Considering Orthogonality of Onset Time

著者名: 山本　清高（中京大学大学院情報科学研究科），村田　晴美（中京大学工学部），荻原　昭夫（近畿大学工学部），目加田　慶人（中京大学大学院情報科学研究科）

著者名(英語): Kiyotaka Yamamoto (Graduate School of Computer and Cognitive Sciences, Chukyo University), Harumi Murata (School of Engineering, Chukyo University), Akio Ogihara (Faculty of Engineering, Kindai University), Yoshito Mekada (Graduate School of Computer and Cognitive Sciences, Chukyo University)

キーワード: 非負値行列因子分解，音高・発音時刻推定，エレキベース　　non-negative matrix factorization，pitch and onset time estimation，electric bass

要約(英語): This paper proposes a new regularization term of non-negative matrix factorization (NMF) for estimating pitch and onset time of electric bass. Both of them are indispensable information for automatic music transcription. However, it is difficult to estimate them from the electric bass performance because of trade-off problem between time resolution and frequency resolution. Applying the NMF simply to the electric bass performance, the correct note and its semitone are sometimes detected simultaneously. The proposed regularization term avoiding such miss detection based on the performance characteristic of the electric bass, that is, two notes are not generally played simultaneously. We define the regularization term in order to keep orthogonality of the adjacent activation decomposed by the NMF. As a result of the experiments using MIDI synthesizer-generated sound of electric bass and real played electric bass sound, it is confirmed that the F-measure of the proposed method is higher than that of comparative method.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.136 No.12 （2016） 特集Ⅰ：電気・電子・情報関係学会東海支部連合大会　特集Ⅱ：国際会議ACIS 2014/2015

本誌掲載ページ: 1661-1667 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/136/12/136_1661/_article/-char/ja/